分组选择聚类融合算法  

Sub-grouping and selecting method of cluster fusion

作　　者：孔志周[1] 蔡自兴[1] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083

出　　处：《控制与决策》2012年第3期369-373,共5页Control and Decision

基　　金：国家基础研究项目(A1420060159);国家博士点基金项目(200805330005);NSFC重大专项基金项目(90820302)

摘　　要：针对聚类融合算法可能出现信息失真等问题,提出一种新的聚类融合算法.该算法兼顾聚类质量与成员多样性,采用一种新的相似性度量,并依据度量结果先对聚类成员进行剪辑操作,再分组、选择,最后根据每个聚类成员对于各类别的贡献设计了一种新的加权函数.与其他方法相比,该方法具有较好的稳定性和精确性.For information distortion of cluster fusion algorithm, a new cluster fusion algorithm is proposed, which gives consideration to both the cluster quality and the diversity of cluster members, and adopts a new method of similarity measurement. According to the measure result, cluster members are edited, subgrouped and selected, finally a new weighting function is designed based on the contribution of each cluster member to each category. The practice results show that the algorithm has better stability and precise compared with other methods.

关 键 词：聚类融合 剪辑 分组选择 加权函数 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]